Mistral · Mistral · Reviewed 2026-10-02

Mistral Medium 3.5

Mistral's open-weight multimodal model for coding and agentic workflows.

All models

Overall · 0–10016.2

Status: active
Released: 2026-04-28
Context: 256,000 tokens
Parameters: Undisclosed
Inputs: Text · Image
Type: multimodal
Max output: — tokens
API model ID: mistral-medium-3-5
Reasoning: —
Knowledge cutoff: —
Training cutoff: —
Weights / license: Available · Modified MIT
Price / 1M tokens: $1.5 in · $7.5 out
Cached input: —

Independent benchmark scores

Independently evaluated

Coding

Terminal-Bench 4.0 in the Artificial Analysis evaluation harness.

Artificial Analysis · AA evaluated Medium 3.5 configuration

Independently evaluated

Reasoning

14%

Humanity's Last Exam as evaluated by Artificial Analysis; the source configuration is preserved.

Artificial Analysis · AA evaluated Medium 3.5 configuration

Independently evaluated

Research

747 Elo

GDPval-AA v2.1 professional knowledge-work Elo. This is a task lens, not an assessment of every research skill.

Artificial Analysis · AA evaluated Medium 3.5 configuration

Independently evaluated

Multimodal

GDP.pdf professional document understanding, including visual tables, charts and diagrams; not an audio/video score.

Artificial Analysis · AA evaluated Medium 3.5 configuration

Independently evaluated

Agentic

AutomationBench-AA multi-step business workflows in the Artificial Analysis harness.

Artificial Analysis · AA evaluated Medium 3.5 configuration

Raw benchmark results

Source-backed rows with the original evaluation context preserved.

6 results

Benchmark	Score	Source	Evaluation notes
AutomationBench-AAChecked 2026-10-02	6%	Artificial Analysis	Artificial Analysis Intelligence Index v4.3.2; configuration=AA evaluated Medium 3.5 configuration. Rounded public score; checked date is not the evaluation execution date.
AA GDP.pdfChecked 2026-10-02	3%	Artificial Analysis	Artificial Analysis Intelligence Index v4.3.2; configuration=AA evaluated Medium 3.5 configuration. Rounded public score; checked date is not the evaluation execution date.
GDPval-AA v2.1Checked 2026-10-02	747	Artificial Analysis	Artificial Analysis Intelligence Index v4.3.2; configuration=AA evaluated Medium 3.5 configuration. Rounded public score; checked date is not the evaluation execution date.
AA Humanity's Last ExamChecked 2026-10-02	14%	Artificial Analysis	Artificial Analysis Intelligence Index v4.3.2; configuration=AA evaluated Medium 3.5 configuration. Rounded public score; checked date is not the evaluation execution date.
Artificial Analysis Intelligence Index v4.3.2Checked 2026-10-02	14	Artificial Analysis	Artificial Analysis Intelligence Index v4.3.2; configuration=AA evaluated Medium 3.5 configuration. Rounded public score; checked date is not the evaluation execution date.
AA Terminal-Bench 4.0Checked 2026-10-02	0%	Artificial Analysis	Artificial Analysis Intelligence Index v4.3.2; configuration=AA evaluated Medium 3.5 configuration. Rounded public score; checked date is not the evaluation execution date.

Strengths

Open weights
Visual input
Coding and agentic tasks

Limitations

Unconfirmed specifications remain undisclosed; missing evaluation results remain unranked

Model evidence · official · Checked 2026-10-02

Mistral Medium 3.5 model documentation

Official release or model documentation reviewed 2026-10-02; unconfirmed fields are left unset.

Capability Index source

Artificial Analysis Intelligence Index v4.3.2

Underlying raw metrics and exact model configurations remain authoritative.

Capability Index source

Artificial Analysis methodology

Underlying raw metrics and exact model configurations remain authoritative.

Task lenses preserve raw scores. Radar axes use score / current leader × 100; overall is the equal-weight average of all five indices. Missing evidence is not a zero or a low rank.